start_2fa

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden. It discloses side effects (sends a code), conditional return values (deep_link, qr_code, qr_text, session_id), the email requires_email_selection case where no session is created, and that email may deliver a magic link instead of a code. It also states the access prerequisite clearly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-organized with a front-loaded purpose and a numbered flow. Some channel instructions are repeated in different forms, which adds a little redundancy, but the complexity of the 2FA flow justifies most of the detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must explain return values and edge cases itself. It covers session_id, channel-specific artifacts, email selection, SMS flow, the no-session case, magic-link handling, polling, and access setup. An agent has enough context to invoke the tool correctly in real scenarios.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds meaningful conditional semantics: when email_id is needed, how channel changes the response and user action, and how action_type fits into the flow. It does not detail every action_type value, but the schema already enumerates and describes them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that this tool starts a 2FA challenge, sends a verification code, and returns a session ID plus channel-specific artifacts. However, it never distinguishes itself from the near-named sibling start_2fa_for_action, so an agent could be uncertain which of the two starting tools to choose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a full, numbered agent workflow: when to call the tool, how to handle each channel, when to re-call with email_id, when to poll get_2fa_status, and what to do on verified or expired outcomes. It also gives explicit prohibitions, such as not announcing unsent messages and never handing qr_text to a link renderer.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.